{"id":106703,"date":"2025-02-20T07:59:45","date_gmt":"2025-02-20T13:59:45","guid":{"rendered":"https:\/\/engineering.wisc.edu\/?post_type=tribe_events&p=106703"},"modified":"2025-02-26T12:21:51","modified_gmt":"2025-02-26T18:21:51","slug":"engineering-robust-scalable-ai-for-healthcaresystems","status":"publish","type":"tribe_events","link":"https:\/\/engineering.wisc.edu\/event\/engineering-robust-scalable-ai-for-healthcaresystems\/","title":{"rendered":"ISyE Engineering Robust & Scalable AI for Healthcare Systems"},"content":{"rendered":"
\n\t

\n\t\t\n\t\t\tMarch 3\t\t<\/span>\n\n\t\t\t\t\t\n\t\t\t\t @ \t\t\t<\/span>\n\t\t\t\n\t\t\t\t11:30 AM\t\t\t<\/span>\n\t\t\n\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t – \t\t\t\t<\/span>\n\t\t\t\n\t\t\t\t\t\t\t\n\t\t\t\t\t12:30 PM\t\t\t\t<\/span>\n\t\t\t\n\t\t\t\t\t\t<\/h2>\n<\/div>\n\n\n\n
\"\"<\/figure>\n\n\n\n

Artificial intelligence (AI) is increasingly used in healthcare to enhance clinical decision-making,
optimize operations, and improve patient outcomes. However, real-world deployment of AI
systems presents fundamental engineering challenges, including dataset shifts, physician-AI
team dynamics, and the need for continuous model validation and updating. These challenges
threaten the reliability and scalability of AI tools, limiting their ability to provide consistent value
in clinical environments.<\/p>\n\n\n\n


In this talk, I will present engineering solutions that address these core challenges and enable
the development of AI systems that are both scalable and safe. First, I will discuss techniques
for integrating longitudinal patient data into predictive models, improving their performance
over time. Second, I will introduce methods to detect and mitigate dataset shifts, ensuring
models maintain accuracy when transitioning from development to real-world use. Finally, I will
describe a novel rank-based compatibility measure and optimization framework that improves
model updating while preserving physician trust and workflow stability.<\/p>\n\n\n\n


By developing these foundational methods, my work moves healthcare AI from an artisanal,
model-by-model approach to a scalable engineering discipline. I will conclude by discussing
future research directions, including AI personalization for individual physicians and the
development of interactive AI validation systems that continuously adapt based on clinician
feedback.<\/p>\n\n\n

\n\t\n\t\n
\n\t
\n\t\t

1153 Mechanical Engineering<\/a><\/h3>\n\t<\/div>\n\n\t\n\t\t\t
\n\t\t\t\n\n1513 University Ave<\/span>\n\t\n\t\t
\n\t\tMadison<\/span>,<\/span>\n\n\tWI<\/abbr>\n\n\t53706<\/span>\n\n\tUnited States<\/span>\n\n<\/span>\n\n\t\t\t\t\t<\/address>\n\t\n\t\n\t\n\t<\/div>\n\t\n\t<\/div>\n\n\n\n

Bio:<\/strong> Erkin \u00d6tle\u015f, MD, PhD, is an engineer with deep medical expertise, specializing in developing
methods to create scalable and robust artificial intelligence systems for healthcare. His
research addresses the core engineering challenges of AI deployment in real-world clinical
settings\u2014detecting and mitigating dataset shifts, designing AI systems that integrate
seamlessly into physician workflows, and creating novel methods for continuous validation and
model updating.
<\/p>\n\n\n\n

Dr. \u00d6tle\u015f has developed innovative machine learning techniques to model longitudinal patient
trajectories, optimize human-AI collaboration in clinical decision-making, and enhance the
safety and interpretability of AI tools in high-stakes environments. His work has been published
in leading medical (JAMA Internal Medicine, The BMJ) and engineering (Machine Learning for
Healthcare, Journal of the American Medical Informatics Association) venues, demonstrating
his ability to bridge theoretical advancements with practical implementation. His research has
also been widely covered by the lay press, including NPR, WIRED, and STAT News,
underscoring its broad societal impact.<\/p>\n\n\n\n


As an engineer and a physician, Dr. \u00d6tle\u015f brings a unique systems perspective to AI in
healthcare. His work aims to transition healthcare AI development, evaluation, and
implementation from an artisanal, model-by-model process to a scalable engineering discipline
\u2014ensuring that AI tools used in medicine are not only powerful and plentiful but also safe,
reliable, and adaptable to dynamic clinical environments.<\/p>\n\n\n\n\n\t

\n\t\t
\n\t\t\t